RESUMO
Background: The use of antifoaming and mucolytic agents prior to upper gastrointestinal (GI) endoscopy and a thorough systematic review are essential to optimize lesion detection. This study evaluated the effect of simethicone and N-acetylcysteine on the adequate mucosal visibility (AMV) of the upper GI tract by an innovative systematic method. Methods: This randomized, double-blind controlled trial included consecutive patients who underwent diagnostic upper GI endoscopy for screening for early neoplasms between August 2019 and December 2019. The upper GI tract was systematically assessed by systematic alphanumeric-coded endoscopy. Patients were divided into 4 groups: 1) water; 2) only simethicone; 3) N-acetylcysteine + simethicone; and 4) only N-acetylcysteine. The following parameters were assessed in each group: age, sex, body mass index, level of adequate mucosal visibility, and side-effects. Results: A total of 4564 images from upper GI areas were obtained for evaluation. The mean AMV in the 4 groups was 93.98±7.36%. The N-acetylcysteine + simethicone group had a higher cleaning percentage compared with the other groups (P=0.001). There was no significant difference among the remaining groups, but several areas had better cleaning when a mucolytic or antifoam alone was used. No side-effects were found in any group. Conclusion: The combination of N-acetylcysteine plus simethicone optimizes the visibility of the mucosa of the upper GI tract, which could potentially increase diagnostic yield.
RESUMO
Artificial Intelligence (AI) has the potential to change many aspects of healthcare practice. Image discrimination and classification has many applications within medicine. Machine learning algorithms and complicated neural networks have been developed to train a computer to differentiate between normal and abnormal areas. Machine learning is a form of AI that allows the platform to improve without being programmed. Computer Assisted Diagnosis (CAD) is based on latency, which is the time between the captured image and when it is displayed on the screen. AI-assisted endoscopy can increase the detection rate by identifying missed lesions. An AI CAD system must be responsive, specific, with easy-to-use interfaces, and provide fast results without substantially prolonging procedures. AI has the potential to help both, trained and trainee endoscopists. Rather than being a substitute for high-quality technique, it should serve as a complement to good practice. AI has been evaluated in three clinical scenarios in colonic neoplasms: the detection of polyps, their characterization (adenomatous vs. non-adenomatous) and the prediction of invasive cancer within a polypoid lesion.
La inteligencia artificial (IA) tiene el potencial de cambiar muchos aspectos de la práctica sanitaria. La discriminación y la clasificación de imágenes tiene muchas aplicaciones dentro de la medicina. Se han desarrollado algoritmos de aprendizaje automático y redes neuronales complicadas para entrenar a una computadora a diferenciar las áreas normales de las anormales. El aprendizaje automático es una forma de IA que permite que la plataforma mejore sin ser programada. El diagnóstico asistido por computadora (CAD) se basa en latencia, que es el tiempo entre la imagen capturada y cuando es mostrada en la pantalla. La endoscopia asistida por IA puede incrementar la tasa de detección al identificar lesiones obviadas. Un sistema CAD de IA debe ser sensible, específico, con interfaces fáciles de usar, y proporcionar resultados rápidos sin prolongar sustancialmente los procedimientos. La IA tiene el potencial de ayudar tanto a endoscopistas entrenados como a los que están en entrenamiento. En vez de ser un sustituto para una técnica de alta calidad, deberá servir como un complemento de las buenas prácticas. La IA ha sido evaluada en tres escenarios clínicos en las neoplasias colónicas: la detección de pólipos, su caracterización (adenomatosos vs. no adenomatosos) y la predicción de cáncer invasor dentro de una lesión polipoide.
Assuntos
Inteligência Artificial , Neoplasias do Colo , Humanos , Algoritmos , Neoplasias do Colo/diagnóstico , Instalações de Saúde , Aprendizado de MáquinaRESUMO
BACKGROUND: Endoscopic ultrasound (EUS) -guided fine-needle aspiration (FNA) is a recently described diagnostic method that has demonstrated its usefulness in certain clinical conditions. MATERIAL AND METHODS: Descriptive and retrospective analysis of the initial experience with EUS-guided FNA at the Hospital General "Dr Manuel Gea González", during the period between March, 1998 and December, 1999. A Pentax FG 32UA linear echoendoscope was used for all cases, as well as two different types of needles. Procedures were performed under sedation and a cytopathologist was not present during the FNA. The biopsy site, quality of the material obtained, cytological as well as final diagnosis and complications are described. RESULTS: A total of 40 procedures were done. FNA was performed on the pancreas, esophagus, stomach, duodenum, mediastinum, rectum and lymph nodes. A diagnosis was obtained in 75%. In the remaining cases, the material obtained was either inadequate or insufficient for diagnosis. FNA results were confirmed histologically in all cases that underwent surgery. Complication presented in 2.5%, and consisted of one case of self-limited and clinically irrelevant bleeding. The best results were obtained in lymph nodes, mediastinum, liver and pancreatic tumors. CONCLUSIONS: This study demonstrated the utility of EUS-guided FNA to obtain cytologic material for diagnosis in a high percentage of cases and with minimal complications. Some factors that could lead to better results were also identified.
Assuntos
Biópsia por Agulha/métodos , Endossonografia , Neoplasias Gastrointestinais/diagnóstico por imagem , Neoplasias Gastrointestinais/patologia , Humanos , México , Estudos RetrospectivosRESUMO
El citrato de ranitidina bismuto (CRB) (GR122311X) es un nuevo fármaco con propiedades antisecretoras, citoprotectoras y de erradicación de Helicobacter pylori. Diversos estudios han demostrado que su asociación a claritromicina y amoxicilina logra porcentajes de erradicación con rango de 82 a 94 por ciento con muy pocos eventos adversos relacionados. Objetivo: Determinar la eficacia de citrato de ranitidina bismuto en combinación con claritromicina para erradicar Helicobacter pylori en nuestra población. Material y métodos: Se realizó un estudio prospectivo, aleatorio, doble ciego, comparativo en 80 pacientes con gastritis crónica superficial asociada a Helicobacter pylori. Un grupo recibió citrato de ranitidina bismuto 400 mg BID más claritromicina 250 mg QDS y el otro placebo de CRB BID más claritromicina 250 mg QDS durante dos semanas. Se realizó panendoscopia con prueba rápida de urea (cloTest) y prueba de aliento al inicio del protocolo. La prueba final para evaluar erradicación fue la prueba de aliento. Resultados: La asociación de citrato de ranitidina bismuto 400 mg BID con claritromicina 250 mg QDS logró 86 por ciento de erradicación de la bacteria documentado por prueba de aliento con carbono 13 observando adecuada tolerancia y perfil de seguridad. Conclusiones: El citrato de ranitidina bismuto asociado a claritromicina es una alternativa eficaz y segura de manejo en pacientes con infección por Helicobacter pylori. Futuros estudios se requieren para determinar eficacia y seguridad de claritromicina 500 mg BID o la combinación de dos antibióticos administrados por periodos de siete días en nuestra población.